Comment by bcjdjsndon 6 hours ago Isn't all this massively dependent on what they trained the llm on? 1 comment bcjdjsndon Reply locknitpicker 2 hours ago > Isn't all this massively dependent on what they trained the llm on?The article is from 2025 and tested ChatGPT 4o. I haven't read anything suggesting it was trained any differently, and command-style prompts indeed have higher signal.
locknitpicker 2 hours ago > Isn't all this massively dependent on what they trained the llm on?The article is from 2025 and tested ChatGPT 4o. I haven't read anything suggesting it was trained any differently, and command-style prompts indeed have higher signal.
> Isn't all this massively dependent on what they trained the llm on?
The article is from 2025 and tested ChatGPT 4o. I haven't read anything suggesting it was trained any differently, and command-style prompts indeed have higher signal.